Optimal market timing strategies for ARMA (1,1) return processes

Wei Li, Kin Lam

Research output: Chapter in book/report/conference proceedingChapterpeer-review

Abstract

In this paper, we consider optimal market timing strategies under transaction costs. We assume that the asset's return follows an ARMA (1, 1) model and use long-term investment growth as the objective of a market timing strategy which entails the shifting of funds between a risky asset and a riskless asset. By the use of stochastic dynamic programming techniques, we derive the optimal trading strategies for finite investment horizon, and analyze its limiting behavior. For finite horizon, the optimal decision in each step depends on two control variables. When investment horizon tends to infinity, we prove that the optimal strategy converges to a stationary policy, which also depends on two control variables. An integral equation of the two control variables is given. Numerical solutions and average returns associated with the limiting stationary strategy are also presented. Numerical results confirm that the no-transaction region increases as the transaction cost increases. Finally, the limiting stationary strategy is simulated using data in the Hang Seng Index Futures market in Hong Kong. The out-of-sample performance of the limiting stationary strategy is found to be comparable to that of a buy-and-hold strategy.
Original languageEnglish
Title of host publicationAdvances in Investment Analysis and Portfolio Management. Volume 7
EditorsCheng-Few Lee
PublisherJAI Press
Pages163-190
Number of pages28
Edition1st
ISBN (Print)9780762306589
Publication statusPublished - 20 Dec 2000
Externally publishedYes

Fingerprint

Dive into the research topics of 'Optimal market timing strategies for ARMA (1,1) return processes'. Together they form a unique fingerprint.

Cite this